Usafiri MCP Server

usafiri-mcp

Local serverstdio

What is the Usafiri MCP server?

Usafiri MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. usafiri-mcp.

What you get

MCP server for Kenya transport — matatu routes, NTSA services, boda-boda licensing, freight logistics, and passenger rights. 5 tools.

Setting it up

Installation goes through your MCP client rather than a global install: point it at usafiri-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

What the assistant can call

Once Usafiri is connected, these are the calls the assistant has available:

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the usafiri mcp server does with a few real requests.

Choosing this one

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Usafiri's toolset — Datasets — is a fair guide to whether it matches your workflow. It is maintained by gabrielmahia; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Usafiri's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
Datasets** [huggingface.co/gmahia](https://huggingface.co/gmahia) · **Docs hub:** [nairobi-stack](https://github.com/gabrielmahia/nairobi-stack)

How to install the Usafiri MCP server

{
  "mcpServers": {
    "usafiri": {
      "command": "uvx",
      "args": ["usafiri-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Usafiri to Datasets.

Frequently asked questions

It connects Usafiri to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Datasets) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Usafiri directly.